Qwen 2.5 1.5B: benchmark results
Provider: Alibaba. Released 2024-09-19. Access: Open.
Unified ELO 1378 ± 1, rank #1198 of 1392 rated models, from 211 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Arabic LLM - Arabic MMLU HT Abstract Algebra | 32 | Accuracy (%) | 66 |
| Open Japanese LLM - Mbpp Pylint Check | 62.45 | Score (%) | 61.3 |
| LA Leaderboard - AQuAS | 66.02 | Accuracy (%) | 58.8 |
| Open Japanese LLM - CG | 23.69 | Score (%) | 58.3 |
| Open Arabic LLM - Arabic MMLU Civics (High School) | 44.83 | Accuracy (%) | 56.5 |
| LA Leaderboard - EusExams Basque | 30.98 | Accuracy (%) | 51.1 |
| On Stable Long-Form Generation | 19.6 | LVC (self-reported) | 50 |
| Open LLM Leaderboard - MATH Level 5 | 9.14 | Score | 44.7 |
| Open Arabic LLM - Arabic MMLU HT High School Mathematics | 26.67 | Accuracy (%) | 40.4 |
| Open LLM Leaderboard - GPQA | 4.7 | Score | 40.2 |
| Open Arabic LLM - Arabic MMLU HT Moral Scenarios | 24.69 | Accuracy (%) | 39.2 |
| Open Arabic LLM - Arabic MMLU HT Global Facts | 30 | Accuracy (%) | 37.7 |
Interactive version: theaggregate.ai/model?slug=qwen-2-5-1-5b · How It Works · Data refreshed daily, snapshot 2026-09-05.